nielsr HF staff fcakyon commited on
Commit
df9bcb1
1 Parent(s): 3da1913

fix code snippet in model card (#3)

Browse files

- fix code snippet in model card (18f67186e115131c4df8d89788d8d3356da506aa)
- Update README.md (595e15554a3c0eafb01c367e9ef0016658f7655a)


Co-authored-by: Fatih <[email protected]>

Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -20,16 +20,16 @@ You can use the raw model for video classification into one of the 600 possible
20
  Here is how to use this model to classify a video:
21
 
22
  ```python
23
- from transformers import TimesformerFeatureExtractor, TimesformerForVideoClassification
24
  import numpy as np
25
  import torch
26
 
27
  video = list(np.random.randn(8, 3, 224, 224))
28
 
29
- feature_extractor = TimesformerFeatureExtractor.from_pretrained("facebook/timesformer-base-finetuned-k600")
30
  model = TimesformerForVideoClassification.from_pretrained("facebook/timesformer-base-finetuned-k600")
31
 
32
- inputs = feature_extractor(video, return_tensors="pt")
33
 
34
  with torch.no_grad():
35
  outputs = model(**inputs)
 
20
  Here is how to use this model to classify a video:
21
 
22
  ```python
23
+ from transformers import AutoImageProcessor, TimesformerForVideoClassification
24
  import numpy as np
25
  import torch
26
 
27
  video = list(np.random.randn(8, 3, 224, 224))
28
 
29
+ processor = AutoImageProcessor.from_pretrained("facebook/timesformer-base-finetuned-k600")
30
  model = TimesformerForVideoClassification.from_pretrained("facebook/timesformer-base-finetuned-k600")
31
 
32
+ inputs = processor(images=video, return_tensors="pt")
33
 
34
  with torch.no_grad():
35
  outputs = model(**inputs)